oegeyilmaz9/seo-aeo-geo-ultimate / skills/seo-schema
seo-schema
VerifiedUse when detecting, validating, planning, or generating truthful Schema.org markup tied to visible page content and current search-feature documentation; do not use it to promise rich results, AI citations, or rankings.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.3 KB |
| agents/openai.yaml | config | 433 B |
| references/markdown-delivery-contract.md | markdown | 4.2 KB |
| references/structured-data-review-protocol.md | markdown | 1.3 KB |
references/markdown-delivery-contract.md
View on GitHub# Markdown delivery: seo-schema
Every material work step has a substantive Markdown document and a direct link in private `index.md`. Include outcome/status, scope, evidence dates/links, facts vs inferences, decisions, limitations, owner and next destination. Drafts remain draft/provisional until their owning semantic validator passes. Use the suite artifact renderer for validated formal bundles; do not replace immutable JSON, CSV, raw captures or schema.
Lane documents: `schema-review.md; entity-parity.md`.
Keep JSON-LD in its supported format and validate eligibility against visible HTML. Record entity/fact parity with Markdown; do not replace schema with .md or invent an AI-specific schema.
## Public knowledge profile
For authorized public-site implementation, require lowercase `/llms.txt`, `/sitemap.md`, topic maps and substantive `.md` equivalents for every eligible canonical page in the declared scope. These are owner-defined delivery requirements, not universal SEO/AEO/GEO platform requirements. robots.txt, XML sitemaps, feeds, schema and protocol files keep their native formats. One-page or answer-only work stays bounded and records its work note without changing the whole site.
Use reviewed content from the same revision as HTML. Preserve facts, citations, dates, units, locale, media meaning and public access policy. Private reports, analytics, credentials, admin URLs, personalized content and paywalled material never become public mirrors. Every excluded/unknown inventory URL has a private disposition; unknown eligibility or a partial inventory prevents a whole-site-complete claim.
Direct destinations must actually resolve; planned URLs are labelled planned. Verify links, map coverage, source hashes, public output hashes, editorial parity, UTF-8 MIME delivery, cache/deletion refresh, maintenance owner and the chosen canonical/indexing policy. Public Markdown is a content representation, not a crawler permission, schema replacement or evidence that an engine retrieves/cites it.
Native entry points also carry concise navigation hints: robots `#` comments, XML sitemap/index comments, and two reader-facing sentences in llms.txt direct an interested LLM to the actual Markdown map and answer. Preserve all existing crawl rules and native sitemap elements; comments are discovery hints with no guaranteed consumer. The technical/sitemap owners verify protocol invariance, real destinations and delivered comment retention. Read the full contract's “Native entry-point navigation hints” section before editing those sources.
## Shared tools and full contract
Resolve `<suite-root>` from `.seo-suite-runtime.json` beside SKILL.md in Codex, `${CLAUDE_PLUGIN_ROOT}` in Claude Code, or the absolute suite checkout. Read `<suite-root>/docs/MARKDOWN-DISCOVERY.md` before corpus generation/publication. It owns the detailed inventory, routing, native-format exceptions, privacy, acceptance and source-review rules; do not improvise a conflicting contract.
- Public export: `python "<suite-root>/scripts/manage_markdown_site.py" build --inventory <private/inventory.json> --output <new-public-candidate>`.
- Local projection: `python "<suite-root>/scripts/manage_markdown_site.py" validate --manifest <private-manifest.json> --root <public-candidate>`.
- Full live delivery after authorized publication: same tool, `live --manifest ... --root ... --report <private/live-verification.md>`. A failed/rate-limited run is incomplete, never retried in a loop.
- Work index: `python "<suite-root>/scripts/manage_markdown_work.py" --root <private-work> init --title "Work title"`; use `add --id <step-id> --path <step.md> --title "Step title" --status <draft|provisional|completed|blocked|not-applicable> --owner "Owner" --outcome "Actual result"`, then `check --final` before complete closeout. Equivalent maintained tooling is acceptable when these invariants are verified.
The deterministic export verifies parity with supplied reviewed Markdown, not editorial truth or live HTML. Formal AEO/GEO claims still require the pinned Research Pack. Owner-required source navigation/parity work can proceed locally without inventing engine observations. Preserve separate local acceptance, live delivery and provider outcome states.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |